I train datasets "ADEChallengeData2016",But loss is almost the same

[lily10086]

I use your code to train datasets(ADEChallengeData2016),But the loss is almost the same:
epoch: 19 || batch: 92 || l: 3.161138
epoch: 19 || batch: 93 || l: 3.038326
epoch: 19 || batch: 94 || l: 3.166589
epoch: 19 || batch: 95 || l: 3.135044
epoch: 19 || batch: 96 || l: 3.399570
epoch: 19 || batch: 97 || l: 2.850001
epoch: 19 || batch: 98 || l: 3.409142
epoch: 19 || batch: 99 || l: 3.082799
epoch: 19 || batch: 100 || l: 3.092099
epoch: 19 || batch: 101 || l: 3.262898
epoch: 19 || batch: 102 || l: 3.120981
epoch: 19 || batch: 103 || l: 3.275167
epoch: 19 || batch: 104 || l: 3.187988
epoch: 19 || batch: 105 || l: 3.516507
epoch: 19 || batch: 106 || l: 2.979967
epoch: 19 || batch: 107 || l: 3.051030
epoch: 19 || batch: 108 || l: 3.491227
epoch: 19 || batch: 109 || l: 3.281879
epoch: 19 || batch: 110 || l: 3.299110
epoch: 19 || batch: 111 || l: 3.144029

My loss code is following:
loss=tf.reduce_mean((tf.nn.sparse_softmax_cross_entropy_with_logits(logits=vgg_fcn.upscore32,labels=tf.squeeze(mask,squeeze_dims=[3]),name="entropy")))
train = tf.train.AdamOptimizer(0.005).minimize(loss)
batch_size = 15

What should I do?

[GZHermit]

Wow, @lily10086 ,buddy,could you share your program about resolving the dataset(ADEChallengeData2016) with me？Hope for your reply.Thank you very much.

[gaokun556]

dear friend:
i use the loss function to train my network,but i get errors.could you please tell me what should i do about the label(the size of my label is [256,432],but not[width,hight,num_class]).Please.
thank you for ever. @lily10086

[953693623]

dear friend:
Can you tell me how to train this network? I'm new on the job and I have no idea about it.